{"id":212,"date":"2021-06-01T05:00:00","date_gmt":"2021-05-31T20:00:00","guid":{"rendered":"https:\/\/devneko.jp\/wordpress\/?p=212"},"modified":"2021-06-01T05:00:00","modified_gmt":"2021-05-31T20:00:00","slug":"%e3%83%90%e3%82%a4%e3%83%88%e5%88%97%ef%bc%88%e3%83%88%e3%83%bc%e3%82%af%e3%83%b3%e5%8c%96%e3%81%aa%e3%81%97%ef%bc%89%e3%81%a7%e3%81%aet5","status":"publish","type":"post","link":"https:\/\/devneko.jp\/wordpress\/?p=212","title":{"rendered":"\u30d0\u30a4\u30c8\u5217\uff08\u30c8\u30fc\u30af\u30f3\u5316\u306a\u3057\uff09\u3067\u306eT5"},"content":{"rendered":"\n<ul class=\"wp-block-list\"><li><strong>ByT5: Towards a token-free future with pre-trained byte-to-byte models\u00a0<\/strong>[23.5]<br>\u6700\u3082\u5e83\u304f\u4f7f\u308f\u308c\u3066\u3044\u308b\u4e8b\u524d\u8a13\u7df4\u8a00\u8a9e\u30e2\u30c7\u30eb\u306f\u3001\u5358\u8a9e\u307e\u305f\u306f\u30b5\u30d6\u30ef\u30fc\u30c9\u5358\u4f4d\u306b\u5bfe\u5fdc\u3059\u308b\u30c8\u30fc\u30af\u30f3\u306e\u30b7\u30fc\u30b1\u30f3\u30b9\u3067\u52d5\u4f5c\u3059\u308b\u3002 \u6a19\u6e96\u7684\u306a Transformer \u30a2\u30fc\u30ad\u30c6\u30af\u30c1\u30e3\u306f,\u30d0\u30a4\u30c8\u5217\u306e\u51e6\u7406\u306b\u6700\u5c0f\u9650\u306e\u4fee\u6b63\u3092\u52a0\u3048\u3066\u4f7f\u7528\u3067\u304d\u308b\u3053\u3068\u3092\u793a\u3059\u3002 \u307e\u305f\u3001\u30d0\u30a4\u30c8\u30ec\u30d9\u30eb\u306e\u30e2\u30c7\u30eb\u306f\u30ce\u30a4\u30ba\u306b\u5bfe\u3057\u3066\u8457\u3057\u304f\u5805\u7262\u3067\u3042\u308a\u3001\u30b9\u30da\u30eb\u3084\u767a\u97f3\u306b\u654f\u611f\u306a\u30bf\u30b9\u30af\u3067\u3082\u6027\u80fd\u304c\u5411\u4e0a\u3059\u308b\u3053\u3068\u3092\u793a\u3057\u305f\u3002<br><a href=\"http:\/\/arxiv.org\/abs\/2105.13626v1\">\u8ad6\u6587<\/a>\u00a0\u00a0<a href=\"https:\/\/fugumt.com\/fugumt\/paper_check\/2105.13626v1\">\u53c2\u8003\u8a33\uff08\u30e1\u30bf\u30c7\u30fc\u30bf\uff09<\/a>\u00a0 \u00a0(Fri, 28 May 2021 07:03:22 GMT)<ul><li>MeCab\u3092\u7528\u3044\u305f\u5f62\u614b\u7d20\u89e3\u6790\uff08\u5206\u304b\u3061\u66f8\u304d\uff09\u3084sentence piece\u3092\u7528\u3044\u305ftokenize\u306a\u3069\u3092\u305b\u305a\u306b\u4e8b\u524d\u5b66\u7fd2\u3092\u884c\u3046\u3068\u3044\u3046\u8ad6\u6587\u3002<a href=\"https:\/\/fugumt.com\/fugumt\/paper_check\/2103.06874v2\">Fugu-MT \u8ad6\u6587\u7ffb\u8a33(\u6982\u8981): CANINE: Pre-training an Efficient Tokenization-Free Encoder for Language Representation <\/a>\u304c\u601d\u3044\u6d6e\u304b\u3093\u3060\u304c\u305d\u308c\u3088\u308a\u3082\u9032\u3093\u3067\u3044\u308b\u3088\u3046\u3002<\/li><\/ul><\/li><\/ul>\n","protected":false},"excerpt":{"rendered":"<p>ByT5: Towards a token-free future with pre-trained byte-to-byte models\u00a0[23.5]\u6700\u3082\u5e83\u304f\u4f7f\u308f\u308c\u3066\u3044\u308b\u4e8b\u524d\u8a13\u7df4\u8a00\u8a9e\u30e2\u30c7\u30eb\u306f\u3001\u5358\u8a9e\u307e\u305f\u306f\u30b5\u30d6\u30ef\u30fc\u30c9\u5358\u4f4d &hellip; <a href=\"https:\/\/devneko.jp\/wordpress\/?p=212\" class=\"more-link\"><span class=\"screen-reader-text\">&#8220;\u30d0\u30a4\u30c8\u5217\uff08\u30c8\u30fc\u30af\u30f3\u5316\u306a\u3057\uff09\u3067\u306eT5&#8221; \u306e<\/span>\u7d9a\u304d\u3092\u8aad\u3080<\/a><\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[2],"tags":[392,567],"class_list":["post-212","post","type-post","status-publish","format-standard","hentry","category-arxiv","tag-t5","tag-567"],"_links":{"self":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/212","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=212"}],"version-history":[{"count":0,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/212\/revisions"}],"wp:attachment":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=212"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=212"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=212"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}